Downloads · 30 days
10
42% of all-time downloads
finetuned-modelv6
zarifmahir21/finetuned-modelv6
finetuned-modelv6 is a automatic speech recognition model from zarifmahir21. Use it when you need speech turned into text. The card lists the license as mit.
This model is a fine-tuned version of Rohan432/Augmentedonnormal. Rohan432/Augmentedonnormal is a finetuned version of bangla-speech-processing/BanglaASR on Bangla speech data.
All-time downloads
24
Public
Parameters
242M
5.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt3.9 GB · 57%
At a glance
- Task
- Automatic Speech Recognition
- License
- mit
- Model type
- whisper
- Access
- Public
- Created
- Nov 16, 2025
- Updated
- Nov 17, 2025
- SHA
- beef9d1a
Base models
Model card
From the Hugging Face model README
Description
This model is a fine-tuned version of Rohan432/Augmented_on_normal. Rohan432/Augmented_on_normal is a finetuned version of bangla-speech-processing/BanglaASR on Bangla speech data.
Environment:
- Python version: 3.12.12
- PyTorch version: 2.8.0+cu126
- Librosa version: 0.10.1
- NumPy version: 1.26.4
Training Parameters:
- BATCH_SIZE = 4
- GRADIENT_ACCUMULATION_STEPS = 4
- LEARNING_RATE = 2e-5
- WARMUP_STEPS = 200
- NUM_TRAIN_EPOCHS = 8
- LOGGING_STEPS = 50
Validation Set Evaluation:
| Epoch | Training Loss | Validation Loss | WER | Normalized Levenshtein Similarity |
|---|---|---|---|---|
| 0 | 1.447600 | 1.466727 | 13.093923 | 90.565657 |
| 2 | 1.430200 | 1.469819 | 13.425414 | 90.040404 |
| 4 | 1.423800 | 1.461309 | 11.657459 | 91.272727 |
| 6 | 1.424000 | 1.458325 | 11.215470 | 91.545455 |
| 7 | 1.426100 | 1.457540 | 10.939227 | 91.848485 |
- Task
- Automatic Speech Recognition
- Type
- whisper
- License
- mit
- Created
- Nov 16, 2025
- Updated
- Nov 17, 2025